• Journal of Korean Port Research
• /
• v.14 no.3
• /
• pp.321-329
• /
• 2000

Welding is essential for the manufacture of a range of engineering components which may vary from very large structures such as ships and bridges to very complex structures such as aircraft engines, or miniature components for microelectronic applications. Especially, a domestic situation of the welding automation is still depend on the arc sensing system in comparison to the vision sensing system. Specially, the gap-detecting of workpiece using conventional arc sensor is proposed in this study. As a same principle, a welding current varies with the size of a welding gap. This study introduce to the fuzzy membership filter to cancel a high frequency noise of welding current, and ART2 which has the competitive learning network classifies the signal patterns the filtered welding signal. A welding current possesses a specific pattern according to the existence or the size of a welding gap. These specific patterns result in different classification in comparison with an occasion for no welding gap. The patterns in each case of 1mm, 2mm, 3mm and no welding gap are identified by the artificial neural network.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.2
• /
• pp.62-70
• /
• 2007

The aiming ability is a to improve accuracy performance of the firing vehicle. This paper describes the detection method of chatter vibration using disturbance acceleration in the pointing structure. In order to analysis vibration trends of the pointing system occurred during vehicle drive, acceleration data was processed by using data processing algorithm with moving average and Hilbert transform. Specific mode constants of acceleration were obtained under various disturbances. Vehicle velocity, road condition, property of pointing structure were considered as factors which make change of vibration trend in vehicle dynamics. Finally, back propagation neural networks have been applied to the pattern recognition for the classification of vibration signal in various driving conditions. Results of signal processing were compared and analysed.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.05
• /
• pp.175-178
• /
• 1996

The purpose of this thesis is the propose of various signal processing algorithm for the ECG(electrocardiogram) and the design of realtime automated ECG analyzer feasible with these algorithms. The algorithms are composed of (1)filtering procedure fer the estimation and removal of baseline drift, 60Hz power line interference, and muscle artifacts (2)detection procedure of QRS complex and P wave (3)typification procedure for the pattern classification according to the morphologies (4) selection of representative beat, significant point and wave boundary decision procedure and (5) parameter extraction and diagnosis procedure. All verifications are carried out between the algorithms proposed in this paper and other algorithms already proposed by many researchers, for the objective comparison in each procedure. The efficiency of proposed algorithms are demonstrated with the aid of internationally validated CSE database and the performances of filtering procedure are compared on artificial noise signal as well as actual ECG signals with appropriate noise components. for the comparison on the performance of designed automated ECG analyzer, the diagnosis results were compared with ECG analyzer manufactered by Fukuda denshi in Japan.

• The Journal of Korea Robotics Society
• /
• v.13 no.4
• /
• pp.265-271
• /
• 2018

The recent prosthetic technologies pursue to control multi-DOFs (degrees-of-freedom) hand and wrist. However, challenges such as high cost, wear-ability, and motion intent recognition for feedback control still remain for the use in daily living activities. The paper proposes a multi-channel knit band sensor to worn easily for surface EMG-based prosthetic control. The knitted electrodes were fabricated with conductive yarn, and the band except the electrodes are knitted using non-conductive yarn which has moisture wicking property. Two types of the knit bands are fabricated such as sixteen-electrodes for eight-channels and thirty-two electrodes for sixteen-channels. In order to substantiate the performance of the biopotential signal acquisition, several experiments are conducted. Signal to noise ratio (SNR) value of the knit band sensor was 18.48 dB. According to various forearm motions including hand and wrist, sixteen-channels EMG signals could be clearly distinguishable. In addition, the pattern recognition performance to control myoelectric prosthesis was verified in that overall classification accuracy of the RMS (root mean squares) filtered EMG signals (97.84%) was higher than that of the raw EMG signals (87.06%).

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.120-127
• /
• 2019

Passive source depth discrimination has been studied for decades since the source depth can be used for discriminating whether the target is near the surface or submerged. In this thesis, an algorithm for source depth discrimination is proposed based on CIR (Channel Impulse Response) from target-radiated noise (or signal). In order to extract CIR without a known source signal, Ray-based blind deconvolution is used. Subsequently, intersections of CIR pattern, which is characterized by ray arrival time difference, is utilized for discriminating source depth. The proposed algorithm is demonstrated through numerical simulation in ocean waveguide, and verified via the experimental data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.747-752
• /
• 2011

HMMs (Hidden Markov Models) are widely used for biological signal, such as EEG (electroencephalogram) sequence, analysis because of their ability to incorporate sequential information in their structure. A recent trends of research are going after the biological interpretable HMMs, and we need to control the complexity of the HMM so that it has good generalization performance. So, an automatic means of optimizing the structure of HMMs would be highly desirable. In this paper, we described a procedure of classification of motor imagery EEG signals using HMM. The motor imagery related EEG signals recorded from subjects performing left, right hand and foots motor imagery. And the proposed a method that was focus on the validation of the HSA (Harmony Search Algorithm) based optimization for HMM. Harmony search algorithm is sufficiently adaptable to allow incorporation of other techniques. A HMM training strategy using HSA is proposed, and it is tested on finding optimized structure for the pattern recognition of EEG sequence. The proposed HSA-HMM can performs global searching without initial parameter setting, local optima, and solution divergence.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.10
• /
• pp.2586-2594
• /
• 1995

Two phase flow phenomena are observed in many industrial facilities and make much importance of optimum design for nuclear power plant and various heat exchangers. This experimental study has been investigated the classification of the flow pattern, the local void distribution and convective heat transfer in swirl and non-swirl two phase flow under the isothermal and nonisothermal conditions. The convective heat transfer coefficients in the single phase water flow were measured and compared with the calculated results from the Sieder-Tate correlation. These coefficients were used for comparisons with the two-phase heat transfer coefficients in the flow orientations. The experimental results indicate, that the void probe signal and probability density function of void distribution can used into classify the flow patterns, no significant difference in voidage distribution was observed between isothermal and non-isothermal condition in non-swirl flow, the values of two phase heat transfer coefficients increase when superficial air velocities increase, and the enhancement of the values is observed to be most pronounced at the highest superficial water velocity in non-swirl flow. Also two phase heat transfer coefficients in swirl flow are increased when the twist ratios are decreased.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.379-382
• /
• 2006

일반적으로 센서 어레이는 많은 채널의 센서를 가지고 있으므로 분석해야 할 데이터의 양이 많다. 따라서 다변량(多變量) 분석 방법을 이용하는데, 크게 통계적 방법과 신경망 방법을 분석하고자 하는 데이터의 특성이나 분석에 필요한 환경 조건에 맞는 분석 방법을 선택하여 이용한다. 센서 어레이의 신호 패턴을 분석하기 위해 본 연구에서는 상태 천이 모델을 이용하여 측정된 가스의 특성을 반영할 수 있는 통계적 방법에 대해 연구하였다. 센서 어레이 신호 데이터를 패턴 모양의 특성을 나타낼 수 있는 상태 천이 모델로 변환하여 가스 종류 식별이 보다 정확하게 이루어 질 수 있도록 모델을 설계하는데 중점을 두고, 모델링 요소인 '상태'는 일정한 시간 간격으로 샘플링 하였을 때의 신호값으로,'천이 관계는 각 천이 벡터의 각으로 각각 정의하여 각도변이 기반 상태천이 모델링을 고안하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.470-473
• /
• 2004

In this paper, the comparison of speech feature parameters for emotion recognition is studied for emotion recognition using speech signal. For this purpose, a corpus of emotional speech data recorded and classified according to the emotion using the subjective evaluation were used to make statical feature vectors such as average, standard deviation and maximum value of pitch and energy. MFCC parameters and their derivatives with or without cepstral mean subfraction are also used to evaluate the performance of the conventional pattern matching algorithms. Pitch and energy Parameters were used as a Prosodic information and MFCC Parameters were used as phonetic information. In this paper, In the Experiments, the vector quantization based emotion recognition system is used for speaker and context independent emotion recognition. Experimental results showed that vector quantization based emotion recognizer using MFCC parameters showed better performance than that using the Pitch and energy parameters. The vector quantization based emotion recognizer achieved recognition rates of 73.3％ for the speaker and context independent classification.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.818-821
• /
• 2002

In this paper, we propose Neuro-Fuzzy discrimination method of the new and old bill using bill money acoustic data. The concept of the histogram is introduced to improve the processing time into the proposal system. The adaptative filter is used in order to remove the motor sound from an observed bill money acoustic data. The output signal of this adaptive digital filter is converted into not only a spectrum but also a histogram. It became easy that features of the paper money sound were extracted from the bill money acoustic data. The spectral data and the histogram is obtained like this, and it become an input pattern of the neural network(NN). Then, the discrimination result of the NN is finally judged by the fuzzy inferece in the new bill or the exhaustion bill.